© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211601
    Prev
    Next
    INDEX
    Explanations

    investing heavily in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /[
    0.54
    ossal
    0.46
     στον
    0.44
    क्षेप
    0.44
    transpose
    0.42
    ,[
    0.42
    ೫
    0.41
     юк
    0.41
     \\[
    0.41
     Mundial
    0.40
    POSITIVE LOGITS
    ສໍາ
    0.43
     training
    0.42
    fdata
    0.42
     Idani
    0.42
    suites
    0.42
    培训
    0.41
    主播
    0.41
     अभि
    0.41
     personalization
    0.41
    newUser
    0.41
    Activations Density 0.002%

    No Known Activations